Benchmark
GPQA Diamond
Scientific reasoning
- Categories
- intelligence-index, reasoning, science
- Openness
- unknown
- Source
- artificial_analysis
- Reported scores
- 586
Reported scores
artificial_analysis
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| A.X-K2 | SK Telecom | 0.856565656565657 | 2026-08-12 | evidence |
| Agnes 2.5 Pro Alpha | Sapiens AI | 0.875757575757576 | 2026-07-24 | evidence |
| Apertus 70B Instruct | Swiss AI Initiative | 0.271717171717172 | 2025-09-02 | evidence |
| Apertus 8B Instruct | Swiss AI Initiative | 0.255555555555556 | 2025-09-02 | evidence |
| Apriel-v1.5-15B-Thinker | ServiceNow | 0.713131313131313 | 2025-09-30 | evidence |
| Apriel-v1.6-15B-Thinker | ServiceNow | 0.733333333333333 | 2025-11-25 | evidence |
| Celeris-1 | Celeris | 0.631313131313131 | 2026-07-24 | evidence |
| Claude 2.0 | Anthropic | 0.344444444444444 | 2023-07-11 | evidence |
| Claude 2.1 | Anthropic | 0.319191919191919 | 2023-11-21 | evidence |
| Claude 3 Haiku | Anthropic | 0.373737373737374 | 2024-03-04 | evidence |
| Claude 3 Opus | Anthropic | 0.488888888888889 | 2024-03-04 | evidence |
| Claude 3 Sonnet | Anthropic | 0.4 | 2024-03-04 | evidence |
| Claude 3.5 Haiku | Anthropic | 0.408080808080808 | 2024-10-22 | evidence |
| Claude 3.5 Sonnet (June '24) | Anthropic | 0.55959595959596 | 2024-06-21 | evidence |
| Claude 3.5 Sonnet (Oct '24) | Anthropic | 0.598989898989899 | 2024-10-22 | evidence |
| Claude 3.7 Sonnet (Non-reasoning) | Anthropic | 0.655555555555556 | 2025-02-24 | evidence |
| Claude 3.7 Sonnet (Reasoning) | Anthropic | 0.771717171717172 | 2025-02-24 | evidence |
| Claude 4 Opus (Non-reasoning) | Anthropic | 0.701010101010101 | 2025-05-22 | evidence |
| Claude 4 Opus (Reasoning) | Anthropic | 0.795959595959596 | 2025-05-22 | evidence |
| Claude 4 Sonnet (Non-reasoning) | Anthropic | 0.682828282828283 | 2025-05-22 | evidence |
| Claude 4 Sonnet (Reasoning) | Anthropic | 0.776767676767677 | 2025-05-22 | evidence |
| Claude 4.1 Opus (Reasoning) | Anthropic | 0.809 | 2025-08-05 | evidence |
| Claude 4.5 Haiku (Non-reasoning) | Anthropic | 0.646464646464646 | 2025-10-15 | evidence |
| Claude 4.5 Haiku (Reasoning) | Anthropic | 0.671717171717172 | 2025-10-15 | evidence |
| Claude 4.5 Sonnet (Non-reasoning) | Anthropic | 0.727272727272727 | 2025-09-29 | evidence |
| Claude 4.5 Sonnet (Reasoning) | Anthropic | 0.834343434343434 | 2025-09-29 | evidence |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 0.926262626262626 | 2026-06-09 | evidence |
| Claude Instant | Anthropic | 0.33030303030303 | 2023-03-14 | evidence |
| Claude Opus 4.5 (Non-reasoning) | Anthropic | 0.81010101010101 | 2025-11-24 | evidence |
| Claude Opus 4.5 (Reasoning) | Anthropic | 0.865656565656566 | 2025-11-24 | evidence |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 0.895959595959596 | 2026-02-05 | evidence |
| Claude Opus 4.6 (Non-reasoning, High Effort) | Anthropic | 0.84040404040404 | 2026-02-05 | evidence |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 0.914141414141414 | 2026-04-16 | evidence |
| Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic | 0.884848484848485 | 2026-04-16 | evidence |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 0.92020202020202 | 2026-05-28 | evidence |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 0.937373737373737 | 2026-07-24 | evidence |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 0.888888888888889 | 2026-07-24 | evidence |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 0.932323232323232 | 2026-07-24 | evidence |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 0.919191919191919 | 2026-07-24 | evidence |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 0.937373737373737 | 2026-07-24 | evidence |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 0.874747474747475 | 2026-02-17 | evidence |
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic | 0.798989898989899 | 2026-02-17 | evidence |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic | 0.796969696969697 | 2026-02-17 | evidence |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 0.911111111111111 | 2026-06-30 | evidence |
| Claude Sonnet 5 (Non-reasoning, High Effort) | Anthropic | 0.8 | 2026-06-30 | evidence |
| Cogito v2.1 (Reasoning) | Deep Cogito | 0.767676767676768 | 2025-11-18 | evidence |
| Command A | Cohere | 0.527272727272727 | 2025-03-13 | evidence |
| Command A+ | Cohere | 0.760606060606061 | 2026-05-20 | evidence |
| Command-R (Mar '24) | Cohere | 0.283838383838384 | 2024-03-12 | evidence |
| Command-R+ (Apr '24) | Cohere | 0.323232323232323 | 2024-04-04 | evidence |
| DBRX Instruct | Databricks | 0.331313131313131 | 2024-03-27 | evidence |
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research | 0.26969696969697 | 2025-02-13 | evidence |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 0.381818181818182 | 2025-03-13 | evidence |
| DeepSeek Coder V2 Lite Instruct | DeepSeek | 0.319191919191919 | 2024-06-17 | evidence |
| DeepSeek R1 (Jan '25) | DeepSeek | 0.708080808080808 | 2025-01-20 | evidence |
| DeepSeek R1 0528 (May '25) | DeepSeek | 0.813131313131313 | 2025-05-28 | evidence |
| DeepSeek R1 0528 Qwen3 8B | DeepSeek | 0.612121212121212 | 2025-05-29 | evidence |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 0.402020202020202 | 2025-01-20 | evidence |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 0.302020202020202 | 2025-01-20 | evidence |
| DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 0.097979797979798 | 2025-01-20 | evidence |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | 0.483838383838384 | 2025-01-20 | evidence |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 0.615151515151515 | 2025-01-20 | evidence |
| DeepSeek V3 (Dec '24) | DeepSeek | 0.556565656565657 | 2024-12-26 | evidence |
| DeepSeek V3 0324 | DeepSeek | 0.654545454545455 | 2025-03-25 | evidence |
| DeepSeek V3.1 (Non-reasoning) | DeepSeek | 0.735353535353535 | 2025-08-21 | evidence |
| DeepSeek V3.1 (Reasoning) | DeepSeek | 0.778787878787879 | 2025-08-21 | evidence |
| DeepSeek V3.1 Terminus (Non-reasoning) | DeepSeek | 0.750505050505051 | 2025-09-22 | evidence |
| DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 0.791919191919192 | 2025-09-22 | evidence |
| DeepSeek V3.2 (Non-reasoning) | DeepSeek | 0.750505050505051 | 2025-12-01 | evidence |
| DeepSeek V3.2 (Reasoning) | DeepSeek | 0.84040404040404 | 2025-12-01 | evidence |
| DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | 0.738383838383838 | 2025-09-29 | evidence |
| DeepSeek V3.2 Exp (Reasoning) | DeepSeek | 0.796969696969697 | 2025-09-29 | evidence |
| DeepSeek V3.2 Speciale | DeepSeek | 0.870707070707071 | 2025-12-01 | evidence |
| DeepSeek V4 Flash (Non-reasoning) | DeepSeek | 0.716161616161616 | 2026-04-24 | evidence |
| DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | 0.866666666666667 | 2026-04-24 | evidence |
| DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | 0.893939393939394 | 2026-04-24 | evidence |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 0.908080808080808 | 2026-07-31 | evidence |
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | DeepSeek | 0.913131313131313 | 2026-08-21 | evidence |
| DeepSeek V4 Pro (Non-reasoning) | DeepSeek | 0.717171717171717 | 2026-04-24 | evidence |
| DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 0.905050505050505 | 2026-04-24 | evidence |
| DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 0.887878787878788 | 2026-04-24 | evidence |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 0.928282828282828 | 2026-08-13 | evidence |
| DeepSeek-V2.5 (Dec '24) | DeepSeek | 0.423232323232323 | 2024-12-10 | evidence |
| Devstral 2 | Mistral | 0.593939393939394 | 2025-12-09 | evidence |
| Devstral Medium | Mistral | 0.491919191919192 | 2025-07-10 | evidence |
| Devstral Small (Jul '25) | Mistral | 0.414141414141414 | 2025-07-10 | evidence |
| Devstral Small (May '25) | Mistral | 0.434343434343434 | 2025-05-21 | evidence |
| Devstral Small 2 | Mistral | 0.532323232323232 | 2025-12-09 | evidence |
| DiffusionGemma 26B A4B | 0.668686868686869 | 2026-06-10 | evidence | |
| Doubao Seed Code | ByteDance Seed | 0.763636363636364 | 2025-11-11 | evidence |
| ERNIE 4.5 300B A47B | Baidu | 0.811111111111111 | 2025-06-30 | evidence |
| ERNIE 5.0 Thinking Preview | Baidu | 0.776767676767677 | 2025-11-13 | evidence |
| Exaone 4.0 1.2B (Non-reasoning) | LG AI Research | 0.424242424242424 | 2025-07-15 | evidence |
| Exaone 4.0 1.2B (Reasoning) | LG AI Research | 0.515151515151515 | 2025-07-15 | evidence |
| EXAONE 4.0 32B (Non-reasoning) | LG AI Research | 0.628282828282828 | 2025-07-15 | evidence |
| EXAONE 4.0 32B (Reasoning) | LG AI Research | 0.739393939393939 | 2025-07-15 | evidence |
| EXAONE 4.5 33B | LG AI Research | 0.793939393939394 | 2026-04-09 | evidence |
| Falcon-H1R-7B | TII UAE | 0.660606060606061 | 2026-01-04 | evidence |
| G9v3-39A5B | AI9Stars | 0.805050505050505 | 2026-08-20 | evidence |
| G9v3-3B | AI9Stars | 0.438383838383838 | 2026-07-23 | evidence |
| Gemini 1.0 Pro | 0.276767676767677 | 2023-12-06 | evidence | |
| Gemini 1.5 Flash (May '24) | 0.324242424242424 | 2024-05-14 | evidence | |
| Gemini 1.5 Flash (Sep '24) | 0.462626262626263 | 2024-09-24 | evidence | |
| Gemini 1.5 Flash-8B | 0.358585858585859 | 2024-10-03 | evidence | |
| Gemini 1.5 Pro (May '24) | 0.370707070707071 | 2024-05-15 | evidence | |
| Gemini 1.5 Pro (Sep '24) | 0.588888888888889 | 2024-09-24 | evidence | |
| Gemini 2.0 Flash (experimental) | 0.636363636363636 | 2024-12-11 | evidence | |
| Gemini 2.0 Flash (Feb '25) | 0.623232323232323 | 2025-02-05 | evidence | |
| Gemini 2.0 Flash Thinking Experimental (Jan '25) | 0.701010101010101 | 2025-01-21 | evidence | |
| Gemini 2.0 Flash-Lite (Feb '25) | 0.535353535353535 | 2025-02-25 | evidence | |
| Gemini 2.0 Flash-Lite (Preview) | 0.542424242424242 | 2025-02-05 | evidence | |
| Gemini 2.0 Pro Experimental (Feb '25) | 0.622222222222222 | 2025-02-05 | evidence | |
| Gemini 2.5 Flash (Non-reasoning) | 0.682828282828283 | 2025-05-20 | evidence | |
| Gemini 2.5 Flash (Reasoning) | 0.78989898989899 | 2025-05-20 | evidence | |
| Gemini 2.5 Flash Preview (Non-reasoning) | 0.593939393939394 | 2025-04-17 | evidence | |
| Gemini 2.5 Flash Preview (Reasoning) | 0.697979797979798 | 2025-04-17 | evidence | |
| Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 0.765656565656566 | 2025-09-25 | evidence | |
| Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 0.792929292929293 | 2025-09-25 | evidence | |
| Gemini 2.5 Flash-Lite (Non-reasoning) | 0.473737373737374 | 2025-06-17 | evidence | |
| Gemini 2.5 Flash-Lite (Reasoning) | 0.625252525252525 | 2025-06-17 | evidence | |
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 0.65050505050505 | 2025-09-25 | evidence | |
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 0.709090909090909 | 2025-09-08 | evidence | |
| Gemini 2.5 Pro | 0.844444444444444 | 2025-06-05 | evidence | |
| Gemini 2.5 Pro Preview (Mar' 25) | 0.836363636363636 | 2025-03-25 | evidence | |
| Gemini 2.5 Pro Preview (May' 25) | 0.822222222222222 | 2025-05-06 | evidence | |
| Gemini 3 Flash Preview (Non-reasoning) | 0.812121212121212 | 2025-12-17 | evidence | |
| Gemini 3 Flash Preview (Reasoning) | 0.897979797979798 | 2025-12-17 | evidence | |
| Gemini 3 Pro Preview (high) | 0.908080808080808 | 2025-11-18 | evidence | |
| Gemini 3 Pro Preview (low) | 0.886868686868687 | 2025-11-18 | evidence | |
| Gemini 3.1 Flash-Lite | 0.822222222222222 | 2026-03-03 | evidence | |
| Gemini 3.1 Pro Preview | 0.941414141414141 | 2026-02-19 | evidence | |
| Gemini 3.5 Flash (high) | 0.922222222222222 | 2026-05-19 | evidence | |
| Gemini 3.5 Flash (medium) | 0.921212121212121 | 2026-05-19 | evidence | |
| Gemini 3.5 Flash (minimal) | 0.828282828282828 | 2026-05-19 | evidence | |
| Gemini 3.5 Flash-Lite | 0.838383838383838 | 2026-07-21 | evidence | |
| Gemini 3.6 Flash (high) | 0.928282828282828 | 2026-07-21 | evidence | |
| Gemini 3.7 Flash (high) | 0.945454545454545 | 2026-08-13 | evidence | |
| Gemini 3.7 Flash (low) | 0.901010101010101 | 2026-08-13 | evidence | |
| Gemini 3.7 Flash (medium) | 0.921212121212121 | 2026-08-13 | evidence | |
| Gemma 3 12B Instruct | 0.349494949494949 | 2025-03-12 | evidence | |
| Gemma 3 1B Instruct | 0.237373737373737 | 2025-03-13 | evidence | |
| Gemma 3 270M | 0.224242424242424 | 2025-08-14 | evidence | |
| Gemma 3 27B Instruct | 0.428282828282828 | 2025-03-12 | evidence | |
| Gemma 3 4B Instruct | 0.290909090909091 | 2025-03-12 | evidence | |
| Gemma 3n E2B Instruct | 0.229292929292929 | 2025-06-26 | evidence | |
| Gemma 3n E4B Instruct | 0.295959595959596 | 2025-06-26 | evidence | |
| Gemma 3n E4B Instruct Preview (May '25) | 0.277777777777778 | 2025-05-20 | evidence | |
| Gemma 4 12B (Non-reasoning) | 0.660606060606061 | 2026-06-03 | evidence | |
| Gemma 4 12B (Reasoning) | 0.752525252525252 | 2026-06-03 | evidence | |
| Gemma 4 26B A4B (Non-reasoning) | 0.714141414141414 | 2026-04-02 | evidence | |
| Gemma 4 26B A4B (Reasoning) | 0.791919191919192 | 2026-04-02 | evidence | |
| Gemma 4 31B (Non-reasoning) | 0.762626262626263 | 2026-04-02 | evidence | |
| Gemma 4 31B (Reasoning) | 0.856565656565657 | 2026-04-02 | evidence | |
| Gemma 4 E2B (Non-reasoning) | 0.405050505050505 | 2026-04-02 | evidence | |
| Gemma 4 E2B (Reasoning) | 0.433333333333333 | 2026-04-02 | evidence | |
| Gemma 4 E4B (Non-reasoning) | 0.549494949494949 | 2026-04-03 | evidence | |
| Gemma 4 E4B (Reasoning) | 0.575757575757576 | 2026-04-03 | evidence | |
| GLM 5V Turbo (Reasoning) | Z.ai | 0.809090909090909 | 2026-04-01 | evidence |
| GLM-4.5 (Reasoning) | Z.ai | 0.781818181818182 | 2025-07-28 | evidence |
| GLM-4.5-Air | Z.ai | 0.733333333333333 | 2025-07-28 | evidence |
| GLM-4.5V (Non-reasoning) | Z.ai | 0.572727272727273 | 2025-08-11 | evidence |
| GLM-4.5V (Reasoning) | Z.ai | 0.683838383838384 | 2025-08-11 | evidence |
| GLM-4.6 (Non-reasoning) | Z.ai | 0.632323232323232 | 2025-09-30 | evidence |
| GLM-4.6 (Reasoning) | Z.ai | 0.77979797979798 | 2025-09-30 | evidence |
| GLM-4.6V (Non-reasoning) | Z.ai | 0.565656565656566 | 2025-12-08 | evidence |
| GLM-4.6V (Reasoning) | Z.ai | 0.719191919191919 | 2025-12-08 | evidence |
| GLM-4.7 (Non-reasoning) | Z.ai | 0.663636363636364 | 2025-12-22 | evidence |
| GLM-4.7 (Reasoning) | Z.ai | 0.858585858585858 | 2025-12-22 | evidence |
| GLM-4.7-Flash (Non-reasoning) | Z.ai | 0.451515151515151 | 2026-01-19 | evidence |
| GLM-4.7-Flash (Reasoning) | Z.ai | 0.580808080808081 | 2026-01-19 | evidence |
| GLM-5 (Non-reasoning) | Z.ai | 0.665656565656566 | 2026-02-11 | evidence |
| GLM-5 (Reasoning) | Z.ai | 0.82020202020202 | 2026-02-11 | evidence |
| GLM-5-Turbo | Z.ai | 0.847474747474747 | 2026-03-15 | evidence |
| GLM-5.1 (Non-reasoning) | Z.ai | 0.839393939393939 | 2026-04-07 | evidence |
| GLM-5.1 (Reasoning) | Z.ai | 0.867676767676768 | 2026-04-07 | evidence |
| GLM-5.2 (max) | Z.ai | 0.894949494949495 | 2026-06-16 | evidence |
| GLM-5.2 (Non-reasoning) | Z.ai | 0.685858585858586 | 2026-06-16 | evidence |
| GLM-5.3 (max) | Z.ai | 0.917171717171717 | 2026-08-18 | evidence |
| GPT-3.5 Turbo | OpenAI | 0.296969696969697 | 2022-11-30 | evidence |
| GPT-4 | OpenAI | 0.349494949494949 | 2023-03-14 | evidence |
| GPT-4.1 | OpenAI | 0.665656565656566 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.663636363636364 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.512121212121212 | 2025-04-14 | evidence |
| GPT-4o (Aug '24) | OpenAI | 0.521212121212121 | 2024-08-06 | evidence |
| GPT-4o (ChatGPT) | OpenAI | 0.511111111111111 | 2025-02-15 | evidence |
| GPT-4o (March 2025, chatgpt-4o-latest) | OpenAI | 0.654545454545455 | 2025-03-27 | evidence |
| GPT-4o (May '24) | OpenAI | 0.526262626262626 | 2024-05-13 | evidence |
| GPT-4o (Nov '24) | OpenAI | 0.543434343434343 | 2024-11-20 | evidence |
| GPT-4o mini | OpenAI | 0.426262626262626 | 2024-07-18 | evidence |
| GPT-5 (ChatGPT) | OpenAI | 0.685858585858586 | 2025-08-07 | evidence |
| GPT-5 (high) | OpenAI | 0.853535353535353 | 2025-08-07 | evidence |
| GPT-5 (low) | OpenAI | 0.808080808080808 | 2025-08-07 | evidence |
| GPT-5 (medium) | OpenAI | 0.841750841750842 | 2025-08-07 | evidence |
| GPT-5 (minimal) | OpenAI | 0.672727272727273 | 2025-08-07 | evidence |
| GPT-5 Codex (high) | OpenAI | 0.837373737373737 | 2025-09-23 | evidence |
| GPT-5 mini (high) | OpenAI | 0.828282828282828 | 2025-08-07 | evidence |
| GPT-5 mini (medium) | OpenAI | 0.803030303030303 | 2025-08-07 | evidence |
| GPT-5 mini (minimal) | OpenAI | 0.686868686868687 | 2025-08-07 | evidence |
| GPT-5 nano (high) | OpenAI | 0.675757575757576 | 2025-08-07 | evidence |
| GPT-5 nano (medium) | OpenAI | 0.66969696969697 | 2025-08-07 | evidence |
| GPT-5 nano (minimal) | OpenAI | 0.428282828282828 | 2025-08-07 | evidence |
| GPT-5.1 (high) | OpenAI | 0.872727272727273 | 2025-11-13 | evidence |
| GPT-5.1 (Non-reasoning) | OpenAI | 0.643434343434343 | 2025-11-13 | evidence |
| GPT-5.1 Codex (high) | OpenAI | 0.85959595959596 | 2025-11-13 | evidence |
| GPT-5.1 Codex mini (high) | OpenAI | 0.813131313131313 | 2025-11-13 | evidence |
| GPT-5.2 (medium) | OpenAI | 0.863636363636364 | 2025-12-11 | evidence |
| GPT-5.2 (Non-reasoning) | OpenAI | 0.712121212121212 | 2025-12-11 | evidence |
| GPT-5.2 (xhigh) | OpenAI | 0.903030303030303 | 2025-12-11 | evidence |
| GPT-5.2 Codex (xhigh) | OpenAI | 0.898989898989899 | 2025-12-11 | evidence |
| GPT-5.3 Codex (xhigh) | OpenAI | 0.915151515151515 | 2026-02-05 | evidence |
| GPT-5.4 (low) | OpenAI | 0.870707070707071 | 2026-03-05 | evidence |
| GPT-5.4 (Non-reasoning) | OpenAI | 0.748484848484848 | 2026-03-05 | evidence |
| GPT-5.4 (xhigh) | OpenAI | 0.92020202020202 | 2026-03-05 | evidence |
| GPT-5.4 mini (medium) | OpenAI | 0.823232323232323 | 2026-03-17 | evidence |
| GPT-5.4 mini (Non-Reasoning) | OpenAI | 0.606060606060606 | 2026-03-17 | evidence |
| GPT-5.4 mini (xhigh) | OpenAI | 0.874747474747475 | 2026-03-17 | evidence |
| GPT-5.4 nano (medium) | OpenAI | 0.760606060606061 | 2026-03-17 | evidence |
| GPT-5.4 nano (Non-Reasoning) | OpenAI | 0.557575757575758 | 2026-03-17 | evidence |
| GPT-5.4 nano (xhigh) | OpenAI | 0.817171717171717 | 2026-03-17 | evidence |
| GPT-5.5 (high) | OpenAI | 0.932323232323232 | 2026-04-23 | evidence |
| GPT-5.5 (low) | OpenAI | 0.91010101010101 | 2026-04-23 | evidence |
| GPT-5.5 (medium) | OpenAI | 0.926262626262626 | 2026-04-23 | evidence |
| GPT-5.5 (Non-reasoning) | OpenAI | 0.767676767676768 | 2026-04-23 | evidence |
| GPT-5.5 (xhigh) | OpenAI | 0.935353535353535 | 2026-04-23 | evidence |
| GPT-5.5 Instant (June 2026) | OpenAI | 0.823232323232323 | 2026-06-25 | evidence |
| GPT-5.5 Instant (May 2026) | OpenAI | 0.846464646464646 | 2026-05-05 | evidence |
| GPT-5.6 Luna (high) | OpenAI | 0.891919191919192 | 2026-07-09 | evidence |
| GPT-5.6 Luna (low) | OpenAI | 0.835353535353535 | 2026-07-09 | evidence |
| GPT-5.6 Luna (max) | OpenAI | 0.911111111111111 | 2026-07-09 | evidence |
| GPT-5.6 Luna (medium) | OpenAI | 0.858585858585859 | 2026-07-09 | evidence |
| GPT-5.6 Luna (Non-reasoning) | OpenAI | 0.645454545454546 | 2026-07-09 | evidence |
| GPT-5.6 Luna (xhigh) | OpenAI | 0.894949494949495 | 2026-07-09 | evidence |
| GPT-5.6 Sol (high) | OpenAI | 0.928282828282828 | 2026-07-09 | evidence |
| GPT-5.6 Sol (low) | OpenAI | 0.897979797979798 | 2026-07-09 | evidence |
| GPT-5.6 Sol (max) | OpenAI | 0.941414141414141 | 2026-07-09 | evidence |
| GPT-5.6 Sol (medium) | OpenAI | 0.926262626262626 | 2026-07-09 | evidence |
| GPT-5.6 Sol (Non-reasoning) | OpenAI | 0.78989898989899 | 2026-07-09 | evidence |
| GPT-5.6 Sol (xhigh) | OpenAI | 0.931313131313131 | 2026-07-09 | evidence |
| GPT-5.6 Terra (high) | OpenAI | 0.895959595959596 | 2026-07-09 | evidence |
| GPT-5.6 Terra (low) | OpenAI | 0.843434343434343 | 2026-07-09 | evidence |
| GPT-5.6 Terra (max) | OpenAI | 0.925252525252525 | 2026-07-09 | evidence |
| GPT-5.6 Terra (medium) | OpenAI | 0.871717171717172 | 2026-07-09 | evidence |
| GPT-5.6 Terra (Non-reasoning) | OpenAI | 0.746464646464646 | 2026-07-09 | evidence |
| GPT-5.6 Terra (xhigh) | OpenAI | 0.908080808080808 | 2026-07-09 | evidence |
| gpt-oss-120b (high) | OpenAI | 0.781818181818182 | 2025-08-05 | evidence |
| gpt-oss-120b (low) | OpenAI | 0.671717171717172 | 2025-08-05 | evidence |
| gpt-oss-20b (high) | OpenAI | 0.687878787878788 | 2025-08-05 | evidence |
| gpt-oss-20b (low) | OpenAI | 0.611111111111111 | 2025-08-05 | evidence |
| Granite 3.3 8B (Non-reasoning) | IBM | 0.338383838383838 | 2025-04-16 | evidence |
| Granite 4.0 1B | IBM | 0.280808080808081 | 2025-10-28 | evidence |
| Granite 4.0 350M | IBM | 0.260606060606061 | 2025-10-28 | evidence |
| Granite 4.0 H 1B | IBM | 0.262626262626263 | 2025-10-28 | evidence |
| Granite 4.0 H 350M | IBM | 0.256565656565657 | 2025-10-28 | evidence |
| Granite 4.0 H Small | IBM | 0.416161616161616 | 2025-09-22 | evidence |
| Granite 4.0 Micro | IBM | 0.336363636363636 | 2025-09-22 | evidence |
| Granite 4.1 30B | IBM | 0.480808080808081 | 2026-04-29 | evidence |
| Granite 4.1 3B | IBM | 0.314141414141414 | 2026-04-29 | evidence |
| Granite 4.1 8B | IBM | 0.433333333333333 | 2026-04-29 | evidence |
| Grok 2 (Dec '24) | xAI | 0.51010101010101 | 2024-12-12 | evidence |
| Grok 3 | xAI | 0.692929292929293 | 2025-02-19 | evidence |
| Grok 3 mini Reasoning (high) | xAI | 0.790909090909091 | 2025-02-19 | evidence |
| Grok 4 | xAI | 0.876767676767677 | 2025-07-10 | evidence |
| Grok 4 Fast (Non-reasoning) | xAI | 0.606060606060606 | 2025-09-19 | evidence |
| Grok 4 Fast (Reasoning) | xAI | 0.847474747474747 | 2025-09-19 | evidence |
| Grok 4.1 Fast (Non-reasoning) | xAI | 0.637373737373737 | 2025-11-19 | evidence |
| Grok 4.1 Fast (Reasoning) | xAI | 0.852525252525253 | 2025-11-19 | evidence |
| Grok 4.20 0309 (Non-reasoning) | xAI | 0.784848484848485 | 2026-03-10 | evidence |
| Grok 4.20 0309 (Reasoning) | xAI | 0.884848484848485 | 2026-03-10 | evidence |
| Grok 4.20 0309 v2 (Non-reasoning) | xAI | 0.775757575757576 | 2026-04-07 | evidence |
| Grok 4.20 0309 v2 (Reasoning) | xAI | 0.911111111111111 | 2026-04-07 | evidence |
| Grok 4.3 (high) | xAI | 0.901010101010101 | 2026-04-30 | evidence |
| Grok 4.3 (low) | xAI | 0.843434343434343 | 2026-04-30 | evidence |
| Grok 4.3 (medium) | xAI | 0.88989898989899 | 2026-04-30 | evidence |
| Grok 4.3 (Non-reasoning) | xAI | 0.657575757575758 | 2026-04-30 | evidence |
| Grok 4.5 (high) | xAI | 0.931313131313131 | 2026-07-08 | evidence |
| Grok 4.6 (high) | xAI | 0.94949494949495 | 2026-08-12 | evidence |
| Grok 4.6 (low) | xAI | 0.878787878787879 | 2026-08-12 | evidence |
| Grok 4.6 (medium) | xAI | 0.935353535353535 | 2026-08-12 | evidence |
| Grok 4.6 (xhigh) | xAI | 0.935353535353535 | 2026-08-12 | evidence |
| Grok Beta | xAI | 0.470707070707071 | 2024-08-13 | evidence |
| Grok Build 0.1 0616 | xAI | 0.894949494949495 | 2026-06-16 | evidence |
| Grok Code Fast 1 | xAI | 0.727272727272727 | 2025-08-28 | evidence |
| Hermes 3 - Llama-3.1 70B | Nous Research | 0.401010101010101 | 2024-08-15 | evidence |
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 0.536363636363636 | 2025-08-27 | evidence |
| Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 0.727272727272727 | 2025-08-27 | evidence |
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 0.490909090909091 | 2025-08-27 | evidence |
| Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 0.698989898989899 | 2025-08-27 | evidence |
| Hy3 | Tencent | 0.896969696969697 | 2026-07-06 | evidence |
| Hy3-preview (Non-reasoning) | Tencent | 0.732323232323232 | 2026-04-23 | evidence |
| Hy3-preview (Reasoning) | Tencent | 0.866666666666667 | 2026-04-23 | evidence |
| HyperCLOVA X SEED Think (32B) | Naver | 0.615151515151515 | 2025-12-26 | evidence |
| HyperNova 60B 2605 | Multiverse Computing | 0.733333333333333 | 2026-05-26 | evidence |
| Inkling (xhigh) | Thinking Machines | 0.871717171717172 | 2026-07-15 | evidence |
| Inkling Small | Thinking Machines | 0.894949494949495 | 2026-07-30 | evidence |
| INTELLECT-3 | Prime Intellect | 0.760606060606061 | 2025-11-27 | evidence |
| Jamba 1.5 Large | AI21 Labs | 0.427272727272727 | 2024-08-22 | evidence |
| Jamba 1.5 Mini | AI21 Labs | 0.302020202020202 | 2024-08-22 | evidence |
| Jamba 1.6 Large | AI21 Labs | 0.386868686868687 | 2025-03-06 | evidence |
| Jamba 1.6 Mini | AI21 Labs | 0.3 | 2025-03-06 | evidence |
| Jamba 1.7 Large | AI21 Labs | 0.38989898989899 | 2025-07-07 | evidence |
| Jamba 1.7 Mini | AI21 Labs | 0.322222222222222 | 2025-07-07 | evidence |
| Jamba Reasoning 3B | AI21 Labs | 0.333333333333333 | 2025-10-08 | evidence |
| JT-35B-Flash | China Mobile | 0.829292929292929 | 2026-05-14 | evidence |
| JT-4.1 Flash 236B A21B | China Mobile | 0.845454545454545 | 2026-07-09 | evidence |
| JT-MINI | China Mobile | 0.675757575757576 | 2026-04-15 | evidence |
| K-EXAONE (Non-reasoning) | LG AI Research | 0.694949494949495 | 2025-12-31 | evidence |
| K-EXAONE (Reasoning) | LG AI Research | 0.782828282828283 | 2025-12-31 | evidence |
| K-EXAONE 2.0 0803 | LG AI Research | 0.829292929292929 | 2026-08-12 | evidence |
| K2 Think V2 | MBZUAI Institute of Foundation Models | 0.713131313131313 | 2025-12-15 | evidence |
| K2-V2 (high) | MBZUAI Institute of Foundation Models | 0.680808080808081 | 2025-12-05 | evidence |
| K2-V2 (low) | MBZUAI Institute of Foundation Models | 0.541414141414141 | 2025-12-05 | evidence |
| K2-V2 (medium) | MBZUAI Institute of Foundation Models | 0.597979797979798 | 2025-12-05 | evidence |
| KAT Coder Pro V2 | KwaiKAT | 0.854545454545454 | 2026-03-27 | evidence |
| KAT-Coder-Pro V1 | KwaiKAT | 0.763636363636364 | 2025-11-11 | evidence |
| Kimi K2 | Moonshot AI | 0.765656565656566 | 2025-07-11 | evidence |
| Kimi K2 0905 | Moonshot AI | 0.766666666666667 | 2025-09-05 | evidence |
| Kimi K2 Thinking | Moonshot AI | 0.838383838383838 | 2025-11-06 | evidence |
| Kimi K2.5 (Non-reasoning) | Moonshot AI | 0.788888888888889 | 2026-01-27 | evidence |
| Kimi K2.5 (Reasoning) | Moonshot AI | 0.878787878787879 | 2026-01-27 | evidence |
| Kimi K2.6 | Moonshot AI | 0.911111111111111 | 2026-04-20 | evidence |
| Kimi K2.6 (Non-reasoning) | Moonshot AI | 0.787878787878788 | 2026-04-20 | evidence |
| Kimi K2.7 Code | Moonshot AI | 0.895959595959596 | 2026-06-12 | evidence |
| Kimi K3 (low) | Moonshot AI | 0.842424242424242 | 2026-07-16 | evidence |
| Kimi K3 (max) | Moonshot AI | 0.935353535353535 | 2026-07-16 | evidence |
| Kimi Linear 48B A3B Instruct | Moonshot AI | 0.412121212121212 | 2025-10-30 | evidence |
| LFM 40B | Liquid AI | 0.327272727272727 | 2024-09-30 | evidence |
| LFM2 1.2B | Liquid AI | 0.228282828282828 | 2025-07-10 | evidence |
| LFM2 2.6B | Liquid AI | 0.306060606060606 | 2025-09-23 | evidence |
| LFM2 24B A2B | Liquid AI | 0.473737373737374 | 2026-02-25 | evidence |
| LFM2 8B A1B | Liquid AI | 0.344444444444444 | 2025-10-07 | evidence |
| LFM2.5-1.2B-Instruct | Liquid AI | 0.326262626262626 | 2026-01-05 | evidence |
| LFM2.5-1.2B-Thinking | Liquid AI | 0.339393939393939 | 2026-01-20 | evidence |
| LFM2.5-2.6B | Liquid AI | 0.557575757575758 | 2026-08-04 | evidence |
| LFM2.5-8B-A1B | Liquid AI | 0.513131313131313 | 2026-05-28 | evidence |
| LFM2.5-VL-1.6B | Liquid AI | 0.288888888888889 | 2026-01-05 | evidence |
| Ling 2.6 Flash | InclusionAI | 0.592929292929293 | 2026-04-21 | evidence |
| Ling 3.0 Flash | InclusionAI | 0.854545454545454 | 2026-08-04 | evidence |
| Ling 3.0 Tiny | InclusionAI | 0.734343434343434 | 2026-08-06 | evidence |
| Ling-1T | InclusionAI | 0.719191919191919 | 2025-10-08 | evidence |
| Ling-2.6-1T | InclusionAI | 0.751515151515151 | 2026-04-23 | evidence |
| Ling-flash-2.0 | InclusionAI | 0.656565656565657 | 2025-09-17 | evidence |
| Ling-mini-2.0 | InclusionAI | 0.561616161616162 | 2025-09-09 | evidence |
| Llama 2 Chat 13B | Meta | 0.321212121212121 | 2023-07-18 | evidence |
| Llama 2 Chat 70B | Meta | 0.327272727272727 | 2023-07-18 | evidence |
| Llama 2 Chat 7B | Meta | 0.227272727272727 | 2023-07-18 | evidence |
| Llama 3 Instruct 70B | Meta | 0.378787878787879 | 2024-04-18 | evidence |
| Llama 3 Instruct 8B | Meta | 0.295959595959596 | 2024-04-18 | evidence |
| Llama 3.1 Instruct 405B | Meta | 0.515151515151515 | 2024-07-23 | evidence |
| Llama 3.1 Instruct 70B | Meta | 0.409090909090909 | 2024-07-23 | evidence |
| Llama 3.1 Instruct 8B | Meta | 0.258585858585859 | 2024-07-23 | evidence |
| Llama 3.1 Nemotron Instruct 70B | NVIDIA | 0.464646464646465 | 2024-10-15 | evidence |
| Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 0.408080808080808 | 2025-05-20 | evidence |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 0.728282828282828 | 2025-04-07 | evidence |
| Llama 3.1 Tulu3 405B | Allen Institute for AI | 0.516161616161616 | 2025-01-30 | evidence |
| Llama 3.2 Instruct 11B (Vision) | Meta | 0.221212121212121 | 2024-09-25 | evidence |
| Llama 3.2 Instruct 1B | Meta | 0.195959595959596 | 2024-09-25 | evidence |
| Llama 3.2 Instruct 3B | Meta | 0.254545454545455 | 2024-09-25 | evidence |
| Llama 3.2 Instruct 90B (Vision) | Meta | 0.432323232323232 | 2024-09-25 | evidence |
| Llama 3.3 Instruct 70B | Meta | 0.497979797979798 | 2024-12-06 | evidence |
| Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | NVIDIA | 0.517171717171717 | 2025-03-18 | evidence |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning) | NVIDIA | 0.643434343434343 | 2025-03-18 | evidence |
| Llama 4 Maverick | Meta | 0.670707070707071 | 2025-04-05 | evidence |
| Llama 4 Scout | Meta | 0.586868686868687 | 2025-04-05 | evidence |
| Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 0.480808080808081 | 2025-07-25 | evidence |
| Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | 0.748484848484849 | 2025-07-25 | evidence |
| LongCat 2.0 | LongCat | 0.77979797979798 | 2026-06-29 | evidence |
| LongCat Flash Lite | LongCat | 0.636363636363636 | 2026-01-28 | evidence |
| Magistral Medium 1 | Mistral | 0.678787878787879 | 2025-06-10 | evidence |
| Magistral Medium 1.2 | Mistral | 0.739393939393939 | 2025-09-18 | evidence |
| Magistral Small 1 | Mistral | 0.641414141414141 | 2025-06-10 | evidence |
| Magistral Small 1.2 | Mistral | 0.662626262626263 | 2025-09-17 | evidence |
| Mercury 2 | Inception | 0.76969696969697 | 2026-02-20 | evidence |
| Mi:dm K 2.5 Pro | Korea Telecom | 0.701010101010101 | 2025-12-11 | evidence |
| Mi:dm K 2.5 Pro Preview | Korea Telecom | 0.722222222222222 | 2025-12-11 | evidence |
| MiMo-V2-Flash (Feb 2026) | Xiaomi | 0.835353535353535 | 2025-12-16 | evidence |
| MiMo-V2-Flash (Non-reasoning) | Xiaomi | 0.655555555555556 | 2025-12-16 | evidence |
| MiMo-V2-Flash (Reasoning) | Xiaomi | 0.846464646464647 | 2025-12-16 | evidence |
| MiMo-V2-Omni | Xiaomi | 0.828282828282828 | 2026-03-19 | evidence |
| MiMo-V2-Omni-0327 | Xiaomi | 0.854545454545455 | 2026-03-27 | evidence |
| MiMo-V2-Pro | Xiaomi | 0.86969696969697 | 2026-03-18 | evidence |
| MiMo-V2.5 | Xiaomi | 0.84949494949495 | 2026-04-22 | evidence |
| MiMo-V2.5-Pro | Xiaomi | 0.865656565656566 | 2026-04-22 | evidence |
| MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 0.761616161616162 | 2026-04-22 | evidence |
| MiniCPM-V 4.6 1.3B | OpenBMB | 0.305050505050505 | 2026-05-11 | evidence |
| MiniCPM5-1B (Non-reasoning) | OpenBMB | 0.268686868686869 | 2026-05-25 | evidence |
| MiniCPM5-1B (Reasoning) | OpenBMB | 0.277777777777778 | 2026-05-25 | evidence |
| MiniMax M1 40k | MiniMax | 0.681818181818182 | 2025-06-17 | evidence |
| MiniMax M1 80k | MiniMax | 0.696969696969697 | 2025-06-17 | evidence |
| MiniMax-M2 | MiniMax | 0.776767676767677 | 2025-10-26 | evidence |
| MiniMax-M2.1 | MiniMax | 0.83030303030303 | 2025-12-23 | evidence |
| MiniMax-M2.5 | MiniMax | 0.848484848484848 | 2026-02-12 | evidence |
| MiniMax-M2.7 | MiniMax | 0.873737373737374 | 2026-03-18 | evidence |
| MiniMax-M3 | MiniMax | 0.929292929292929 | 2026-06-01 | evidence |
| Ministral 3 14B | Mistral | 0.571717171717172 | 2025-12-02 | evidence |
| Ministral 3 3B | Mistral | 0.357575757575758 | 2025-12-02 | evidence |
| Ministral 3 8B | Mistral | 0.470707070707071 | 2025-12-02 | evidence |
| Mistral 7B Instruct | Mistral | 0.176767676767677 | 2023-09-27 | evidence |
| Mistral Large (Feb '24) | Mistral | 0.350505050505051 | 2024-02-26 | evidence |
| Mistral Large 2 (Jul '24) | Mistral | 0.471717171717172 | 2024-07-24 | evidence |
| Mistral Large 2 (Nov '24) | Mistral | 0.485858585858586 | 2024-11-18 | evidence |
| Mistral Large 3 | Mistral | 0.67979797979798 | 2025-12-02 | evidence |
| Mistral Medium | Mistral | 0.349494949494949 | 2023-12-11 | evidence |
| Mistral Medium 3 | Mistral | 0.577777777777778 | 2025-05-07 | evidence |
| Mistral Medium 3.1 | Mistral | 0.587878787878788 | 2025-08-12 | evidence |
| Mistral Medium 3.5 | Mistral | 0.748484848484849 | 2026-04-29 | evidence |
| Mistral Saba | Mistral | 0.424242424242424 | 2025-02-17 | evidence |
| Mistral Small (Feb '24) | Mistral | 0.302020202020202 | 2024-02-26 | evidence |
| Mistral Small (Sep '24) | Mistral | 0.380808080808081 | 2024-09-17 | evidence |
| Mistral Small 3 | Mistral | 0.461616161616162 | 2025-01-30 | evidence |
| Mistral Small 3.1 | Mistral | 0.453535353535354 | 2025-03-17 | evidence |
| Mistral Small 3.2 | Mistral | 0.505050505050505 | 2025-06-20 | evidence |
| Mistral Small 4 (Non-reasoning) | Mistral | 0.570707070707071 | 2026-03-16 | evidence |
| Mistral Small 4 (Reasoning) | Mistral | 0.768686868686869 | 2026-03-16 | evidence |
| Mixtral 8x22B Instruct | Mistral | 0.332323232323232 | 2024-04-17 | evidence |
| Mixtral 8x7B Instruct | Mistral | 0.291919191919192 | 2023-12-11 | evidence |
| Molmo 7B-D | Allen Institute for AI | 0.24040404040404 | 2024-09-25 | evidence |
| Molmo2-8B | Allen Institute for AI | 0.425252525252525 | 2025-12-11 | evidence |
| Motif 3 | Motif Technologies | 0.834343434343434 | 2026-08-12 | evidence |
| Motif 3 (Beta) | Motif Technologies | 0.868686868686869 | 2026-07-14 | evidence |
| Motif-2-12.7B-Reasoning | Motif Technologies | 0.694949494949495 | 2025-12-04 | evidence |
| Muse Glimmer (high) | Meta | 0.835353535353535 | 2026-08-10 | evidence |
| Muse Spark | Meta | 0.883838383838384 | 2026-04-08 | evidence |
| Muse Spark 1.1 (xhigh) | Meta | 0.897979797979798 | 2026-07-09 | evidence |
| Muse Spark 1.2 (xhigh) | Meta | 0.904040404040404 | 2026-08-05 | evidence |
| Nanbeige4.1-3B | Nanbeige | 0.84949494949495 | 2026-02-11 | evidence |
| Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 0.468686868686869 | 2026-04-29 | evidence |
| Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 0.8 | 2026-03-11 | evidence |
| Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 0.866666666666667 | 2026-06-04 | evidence |
| Nemotron 3.5 Lightning | NVIDIA | 0.743434343434343 | 2026-08-11 | evidence |
| Nemotron Cascade 2 30B A3B | NVIDIA | 0.757575757575758 | 2026-03-19 | evidence |
| Nex-N2-Pro | Nex AGI | 0.891919191919192 | 2026-06-02 | evidence |
| North Mini Code | Cohere | 0.756565656565657 | 2026-06-09 | evidence |
| Nova 2.0 Lite (high) | Amazon | 0.811111111111111 | 2025-10-29 | evidence |
| Nova 2.0 Lite (low) | Amazon | 0.697979797979798 | 2025-10-29 | evidence |
| Nova 2.0 Lite (medium) | Amazon | 0.767676767676768 | 2025-10-29 | evidence |
| Nova 2.0 Lite (Non-reasoning) | Amazon | 0.603030303030303 | 2025-10-29 | evidence |
| Nova 2.0 Omni (low) | Amazon | 0.698989898989899 | 2025-11-26 | evidence |
| Nova 2.0 Omni (medium) | Amazon | 0.759595959595959 | 2025-11-26 | evidence |
| Nova 2.0 Omni (Non-reasoning) | Amazon | 0.554545454545454 | 2025-11-26 | evidence |
| Nova 2.0 Pro Preview (low) | Amazon | 0.750505050505051 | 2025-11-27 | evidence |
| Nova 2.0 Pro Preview (medium) | Amazon | 0.784848484848485 | 2025-11-27 | evidence |
| Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 0.636363636363636 | 2025-11-27 | evidence |
| Nova Lite | Amazon | 0.433333333333333 | 2024-12-03 | evidence |
| Nova Micro | Amazon | 0.357575757575758 | 2024-12-03 | evidence |
| Nova Premier | Amazon | 0.568686868686869 | 2025-04-30 | evidence |
| Nova Pro | Amazon | 0.498989898989899 | 2024-12-03 | evidence |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | 0.398989898989899 | 2025-12-15 | evidence |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 0.756565656565657 | 2025-12-15 | evidence |
| NVIDIA Nemotron 3 Nano 4B | NVIDIA | 0.513131313131313 | 2026-03-16 | evidence |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA | 0.439393939393939 | 2025-10-28 | evidence |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA | 0.571717171717172 | 2025-10-28 | evidence |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | 0.556565656565657 | 2025-08-18 | evidence |
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 0.56969696969697 | 2025-08-18 | evidence |
| o1 | OpenAI | 0.747474747474747 | 2024-12-05 | evidence |
| o1-mini | OpenAI | 0.603030303030303 | 2024-09-12 | evidence |
| o1-preview | OpenAI | 0.764646464646465 | 2024-09-12 | evidence |
| o3 | OpenAI | 0.827272727272727 | 2025-04-16 | evidence |
| o3-mini | OpenAI | 0.748484848484848 | 2025-01-31 | evidence |
| o3-mini (high) | OpenAI | 0.772727272727273 | 2025-01-31 | evidence |
| o3-pro | OpenAI | 0.845454545454545 | 2025-06-10 | evidence |
| o4-mini (high) | OpenAI | 0.783838383838384 | 2025-04-16 | evidence |
| OLMo 2 32B | Allen Institute for AI | 0.328282828282828 | 2025-03-13 | evidence |
| OLMo 2 7B | Allen Institute for AI | 0.287878787878788 | 2024-11-26 | evidence |
| Olmo 3 32B Think | Allen Institute for AI | 0.61010101010101 | 2025-11-20 | evidence |
| Olmo 3 7B Instruct | Allen Institute for AI | 0.4 | 2025-11-20 | evidence |
| Olmo 3 7B Think | Allen Institute for AI | 0.516161616161616 | 2025-11-20 | evidence |
| Olmo 3.1 32B Instruct | Allen Institute for AI | 0.539393939393939 | 2026-01-13 | evidence |
| Olmo 3.1 32B Think | Allen Institute for AI | 0.590909090909091 | 2025-12-12 | evidence |
| OpenChat 3.5 (1210) | OpenChat | 0.23030303030303 | 2023-12-18 | evidence |
| Phi-3 Mini Instruct 3.8B | Microsoft | 0.319191919191919 | 2024-04-23 | evidence |
| Phi-4 | Microsoft | 0.574747474747475 | 2024-12-12 | evidence |
| Phi-4 Mini Instruct | Microsoft | 0.331313131313131 | 2024-02-26 | evidence |
| Phi-4 Multimodal Instruct | Microsoft | 0.315151515151515 | 2025-02-26 | evidence |
| Pixtral Large | Mistral | 0.505050505050505 | 2024-11-18 | evidence |
| Qwen1.5 Chat 110B | Qwen | 0.288888888888889 | 2024-04-25 | evidence |
| Qwen2 Instruct 72B | Qwen | 0.370707070707071 | 2024-06-07 | evidence |
| Qwen2.5 Coder Instruct 32B | Qwen | 0.417171717171717 | 2024-11-11 | evidence |
| Qwen2.5 Coder Instruct 7B | Qwen | 0.339393939393939 | 2024-09-19 | evidence |
| Qwen2.5 Instruct 32B | Qwen | 0.465656565656566 | 2024-09-19 | evidence |
| Qwen2.5 Instruct 72B | Qwen | 0.490909090909091 | 2024-09-19 | evidence |
| Qwen2.5 Max | Qwen | 0.586868686868687 | 2025-01-28 | evidence |
| Qwen2.5 Turbo | Qwen | 0.41010101010101 | 2024-11-18 | evidence |
| Qwen3 0.6B (Non-reasoning) | Qwen | 0.231313131313131 | 2025-04-28 | evidence |
| Qwen3 0.6B (Reasoning) | Qwen | 0.239393939393939 | 2025-04-28 | evidence |
| Qwen3 1.7B (Non-reasoning) | Qwen | 0.282828282828283 | 2025-04-28 | evidence |
| Qwen3 1.7B (Reasoning) | Qwen | 0.355555555555556 | 2025-04-28 | evidence |
| Qwen3 14B (Non-reasoning) | Qwen | 0.46969696969697 | 2025-04-28 | evidence |
| Qwen3 14B (Reasoning) | Qwen | 0.604040404040404 | 2025-04-28 | evidence |
| Qwen3 235B A22B (Non-reasoning) | Qwen | 0.613131313131313 | 2025-04-28 | evidence |
| Qwen3 235B A22B (Reasoning) | Qwen | 0.7 | 2025-04-28 | evidence |
| Qwen3 235B A22B 2507 (Reasoning) | Qwen | 0.78989898989899 | 2025-07-25 | evidence |
| Qwen3 235B A22B 2507 Instruct | Qwen | 0.752525252525253 | 2025-07-21 | evidence |
| Qwen3 30B A3B (Non-reasoning) | Qwen | 0.515151515151515 | 2025-04-28 | evidence |
| Qwen3 30B A3B (Reasoning) | Qwen | 0.616161616161616 | 2025-04-28 | evidence |
| Qwen3 30B A3B 2507 (Reasoning) | Qwen | 0.707070707070707 | 2025-07-30 | evidence |
| Qwen3 30B A3B 2507 Instruct | Qwen | 0.658585858585859 | 2025-07-29 | evidence |
| Qwen3 32B (Non-reasoning) | Qwen | 0.535353535353535 | 2025-04-28 | evidence |
| Qwen3 32B (Reasoning) | Qwen | 0.667676767676768 | 2025-04-28 | evidence |
| Qwen3 4B (Non-reasoning) | Qwen | 0.397979797979798 | 2025-04-28 | evidence |
| Qwen3 4B (Reasoning) | Qwen | 0.522222222222222 | 2025-04-28 | evidence |
| Qwen3 4B 2507 (Reasoning) | Qwen | 0.666666666666667 | 2025-08-06 | evidence |
| Qwen3 4B 2507 Instruct | Qwen | 0.517171717171717 | 2025-08-06 | evidence |
| Qwen3 8B (Non-reasoning) | Qwen | 0.451515151515152 | 2025-04-28 | evidence |
| Qwen3 8B (Reasoning) | Qwen | 0.588888888888889 | 2025-04-28 | evidence |
| Qwen3 Coder 30B A3B Instruct | Qwen | 0.516161616161616 | 2025-07-31 | evidence |
| Qwen3 Coder 480B A35B Instruct | Qwen | 0.618181818181818 | 2025-07-22 | evidence |
| Qwen3 Coder Next | Qwen | 0.737373737373737 | 2026-02-03 | evidence |
| Qwen3 Max | Qwen | 0.763636363636364 | 2025-09-23 | evidence |
| Qwen3 Max (Preview) | Qwen | 0.763636363636364 | 2025-09-05 | evidence |
| Qwen3 Max Thinking | Qwen | 0.860606060606061 | 2026-01-26 | evidence |
| Qwen3 Max Thinking (Preview) | Qwen | 0.775757575757576 | 2025-11-03 | evidence |
| Qwen3 Next 80B A3B (Reasoning) | Qwen | 0.758585858585858 | 2025-09-11 | evidence |
| Qwen3 Next 80B A3B Instruct | Qwen | 0.738383838383838 | 2025-09-11 | evidence |
| Qwen3 Omni 30B A3B (Reasoning) | Qwen | 0.726262626262626 | 2025-09-22 | evidence |
| Qwen3 Omni 30B A3B Instruct | Qwen | 0.62020202020202 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B (Reasoning) | Qwen | 0.771717171717172 | 2025-09-23 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.712121212121212 | 2025-09-23 | evidence |
| Qwen3 VL 30B A3B (Reasoning) | Qwen | 0.72020202020202 | 2025-10-03 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.694949494949495 | 2025-10-03 | evidence |
| Qwen3 VL 32B (Reasoning) | Qwen | 0.733333333333333 | 2025-10-21 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.670707070707071 | 2025-10-21 | evidence |
| Qwen3 VL 4B (Reasoning) | Qwen | 0.493939393939394 | 2025-10-14 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.370707070707071 | 2025-10-14 | evidence |
| Qwen3 VL 8B (Reasoning) | Qwen | 0.578787878787879 | 2025-10-14 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.427272727272727 | 2025-10-14 | evidence |
| Qwen3.5 0.8B (Non-reasoning) | Qwen | 0.236363636363636 | 2026-03-02 | evidence |
| Qwen3.5 0.8B (Reasoning) | Qwen | 0.111111111111111 | 2026-03-02 | evidence |
| Qwen3.5 122B A10B (Non-reasoning) | Qwen | 0.827272727272727 | 2026-02-24 | evidence |
| Qwen3.5 122B A10B (Reasoning) | Qwen | 0.856565656565657 | 2026-02-24 | evidence |
| Qwen3.5 27B (Non-reasoning) | Qwen | 0.842424242424242 | 2026-02-24 | evidence |
| Qwen3.5 27B (Reasoning) | Qwen | 0.857575757575758 | 2026-02-24 | evidence |
| Qwen3.5 2B (Non-reasoning) | Qwen | 0.438383838383838 | 2026-03-02 | evidence |
| Qwen3.5 2B (Reasoning) | Qwen | 0.455555555555556 | 2026-03-02 | evidence |
| Qwen3.5 35B A3B (Non-reasoning) | Qwen | 0.819191919191919 | 2026-02-24 | evidence |
| Qwen3.5 35B A3B (Reasoning) | Qwen | 0.845454545454545 | 2026-02-24 | evidence |
| Qwen3.5 397B A17B (Non-reasoning) | Qwen | 0.860606060606061 | 2026-02-16 | evidence |
| Qwen3.5 397B A17B (Reasoning) | Qwen | 0.892929292929293 | 2026-02-16 | evidence |
| Qwen3.5 4B (Non-reasoning) | Qwen | 0.712121212121212 | 2026-03-02 | evidence |
| Qwen3.5 4B (Reasoning) | Qwen | 0.770707070707071 | 2026-03-02 | evidence |
| Qwen3.5 9B (Non-reasoning) | Qwen | 0.785858585858586 | 2026-03-02 | evidence |
| Qwen3.5 9B (Reasoning) | Qwen | 0.806060606060606 | 2026-03-02 | evidence |
| Qwen3.5 Omni Flash | Qwen | 0.742424242424242 | 2026-03-30 | evidence |
| Qwen3.5 Omni Plus | Qwen | 0.826262626262626 | 2026-03-30 | evidence |
| Qwen3.6 27B (Non-reasoning) | Qwen | 0.829292929292929 | 2026-04-22 | evidence |
| Qwen3.6 27B (Reasoning) | Qwen | 0.842424242424242 | 2026-04-22 | evidence |
| Qwen3.6 35B A3B (Non-reasoning) | Qwen | 0.817171717171717 | 2026-04-16 | evidence |
| Qwen3.6 35B A3B (Reasoning) | Qwen | 0.841414141414142 | 2026-04-16 | evidence |
| Qwen3.6 Max Preview | Qwen | 0.887878787878788 | 2026-04-20 | evidence |
| Qwen3.6 Plus | Qwen | 0.881818181818182 | 2026-04-02 | evidence |
| Qwen3.7 Max | Qwen | 0.923232323232323 | 2026-05-19 | evidence |
| Qwen3.7 Plus | Qwen | 0.9 | 2026-06-01 | evidence |
| Qwen3.8 2.4T A95B | Qwen | 0.935353535353535 | 2026-08-12 | evidence |
| Qwen3.8 27B (low) | Qwen | 0.845454545454545 | 2026-08-14 | evidence |
| Qwen3.8 27B (medium) | Qwen | 0.845454545454545 | 2026-08-14 | evidence |
| Qwen3.8 27B (Non-reasoning) | Qwen | 0.818181818181818 | 2026-08-14 | evidence |
| Qwen3.8 27B (xhigh) | Qwen | 0.905050505050505 | 2026-08-14 | evidence |
| Qwen3.8 Max | Qwen | 0.927272727272727 | 2026-08-03 | evidence |
| QwQ 32B | Qwen | 0.592929292929293 | 2025-03-05 | evidence |
| QwQ 32B-Preview | Qwen | 0.556565656565656 | 2024-11-27 | evidence |
| Reka Flash 3 | Reka AI | 0.529292929292929 | 2025-03-10 | evidence |
| Ring-1T | InclusionAI | 0.773737373737374 | 2025-10-13 | evidence |
| Ring-2.6-1T | InclusionAI | 0.856565656565657 | 2026-05-08 | evidence |
| Ring-flash-2.0 | InclusionAI | 0.725252525252525 | 2025-09-19 | evidence |
| Sarvam 105B (high) | Sarvam | 0.738383838383838 | 2026-03-06 | evidence |
| Sarvam 30B (high) | Sarvam | 0.633333333333333 | 2026-03-06 | evidence |
| Sarvam M (Reasoning) | Sarvam | 0.416161616161616 | 2025-05-23 | evidence |
| Seed-OSS-36B-Instruct | ByteDance Seed | 0.726262626262626 | 2025-08-20 | evidence |
| Solar Open 100B (Reasoning) | Upstage | 0.656565656565657 | 2025-12-17 | evidence |
| Solar Open2 250B | Upstage | 0.856565656565657 | 2026-08-12 | evidence |
| Solar Pro 2 (Non-reasoning) | Upstage | 0.560606060606061 | 2025-07-09 | evidence |
| Solar Pro 2 (Preview) (Non-reasoning) | Upstage | 0.544444444444445 | 2025-05-20 | evidence |
| Solar Pro 2 (Preview) (Reasoning) | Upstage | 0.577777777777778 | 2025-05-20 | evidence |
| Solar Pro 2 (Reasoning) | Upstage | 0.686868686868687 | 2025-07-09 | evidence |
| Solar Pro 3 | Upstage | 0.724242424242424 | 2026-04-06 | evidence |
| Solar Pro 4 | Upstage | 0.890909090909091 | 2026-08-06 | evidence |
| Sonar | Perplexity | 0.470707070707071 | 2025-01-21 | evidence |
| Sonar Pro | Perplexity | 0.577777777777778 | 2025-01-21 | evidence |
| Sonar Reasoning | Perplexity | 0.623232323232323 | 2025-01-28 | evidence |
| Step 3.5 Flash | StepFun | 0.831313131313131 | 2026-02-02 | evidence |
| Step 3.5 Flash 2603 | StepFun | 0.826262626262626 | 2026-04-02 | evidence |
| Step 3.7 Flash | StepFun | 0.809090909090909 | 2026-05-29 | evidence |
| Step3 VL 10B | StepFun | 0.68989898989899 | 2026-01-20 | evidence |
| Tiny Aya Global | Cohere | 0.305050505050505 | 2026-02-17 | evidence |
| Tri-21B-Think | Trillion Labs | 0.601010101010101 | 2026-02-10 | evidence |
| Tri-21B-think Preview | Trillion Labs | 0.538383838383838 | 2026-02-10 | evidence |
| Trinity Large Thinking | Arcee AI | 0.751515151515151 | 2026-04-01 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.